Add files using upload-large-folder tool

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

configuration_deepseek.py

@@ -0,0 +1,199 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.3"
+}

hf_quant_config.json

@@ -0,0 +1,75 @@
+{
+    "producer": {
+        "name": "modelopt",
+        "version": "0.29.0"
+    },
+    "quantization": {
+        "quant_algo": "NVFP4",
+        "kv_cache_quant_algo": null,
+        "group_size": 16,
+        "exclude_modules": [
+            "lm_head",
+            "model.layers.0.self_attn*",
+            "model.layers.1.self_attn*",
+            "model.layers.10.self_attn*",
+            "model.layers.11.self_attn*",
+            "model.layers.12.self_attn*",
+            "model.layers.13.self_attn*",
+            "model.layers.14.self_attn*",
+            "model.layers.15.self_attn*",
+            "model.layers.16.self_attn*",
+            "model.layers.17.self_attn*",
+            "model.layers.18.self_attn*",
+            "model.layers.19.self_attn*",
+            "model.layers.2.self_attn*",
+            "model.layers.20.self_attn*",
+            "model.layers.21.self_attn*",
+            "model.layers.22.self_attn*",
+            "model.layers.23.self_attn*",
+            "model.layers.24.self_attn*",
+            "model.layers.25.self_attn*",
+            "model.layers.26.self_attn*",
+            "model.layers.27.self_attn*",
+            "model.layers.28.self_attn*",
+            "model.layers.29.self_attn*",
+            "model.layers.3.self_attn*",
+            "model.layers.30.self_attn*",
+            "model.layers.31.self_attn*",
+            "model.layers.32.self_attn*",
+            "model.layers.33.self_attn*",
+            "model.layers.34.self_attn*",
+            "model.layers.35.self_attn*",
+            "model.layers.36.self_attn*",
+            "model.layers.37.self_attn*",
+            "model.layers.38.self_attn*",
+            "model.layers.39.self_attn*",
+            "model.layers.4.self_attn*",
+            "model.layers.40.self_attn*",
+            "model.layers.41.self_attn*",
+            "model.layers.42.self_attn*",
+            "model.layers.43.self_attn*",
+            "model.layers.44.self_attn*",
+            "model.layers.45.self_attn*",
+            "model.layers.46.self_attn*",
+            "model.layers.47.self_attn*",
+            "model.layers.48.self_attn*",
+            "model.layers.49.self_attn*",
+            "model.layers.5.self_attn*",
+            "model.layers.50.self_attn*",
+            "model.layers.51.self_attn*",
+            "model.layers.52.self_attn*",
+            "model.layers.53.self_attn*",
+            "model.layers.54.self_attn*",
+            "model.layers.55.self_attn*",
+            "model.layers.56.self_attn*",
+            "model.layers.57.self_attn*",
+            "model.layers.58.self_attn*",
+            "model.layers.59.self_attn*",
+            "model.layers.6.self_attn*",
+            "model.layers.60.self_attn*",
+            "model.layers.7.self_attn*",
+            "model.layers.8.self_attn*",
+            "model.layers.9.self_attn*"
+        ]
+    }
+}

model-00001-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91e97181ce1a4fea1b4197cb3d6fea651640943ced02751d931df774e6abf75
+size 4832126816

model-00002-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d1bcb509a4ce0a703a8e07286cf9d17f011bc75516bb9bf66eecbff96f498e
+size 2419596008

model-00003-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d9a787411729684af7902d47dc78912e9e8dbc077527681735a90fd132d36f
+size 2419596824

model-00004-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787fa3d30882520d6f158af5c5a7065d8deb5f7ff5d6c0836c959a6847bf1c03
+size 2690157656

model-00005-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb38ce129fdff3a4dcb6b00fd1439a8bfbf3ed35ebe92ba1d0bbec14d7f32885
+size 2419596384

model-00006-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c25d69b98a85b684f5b9ade89761078cd7d0670bb4765784f003b86b82d156
+size 2727777304

model-00007-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3972ce05df1042d327f82bc6f5866c4a2995c09c6aca9a4e7c6a1783ff7c9b
+size 2423266840

model-00008-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86277400e52dc1c5481f0c70646adb2ac59d3c34d13e196d66e383f00c6fd9fa
+size 2419596792

model-00009-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a00d4ce0002c4967623b843347d175bdb8fa049bbc3d00a8291375a30d3d56
+size 2690158040

model-00010-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20dc1ade1e85faa7664b29456dcb0b20d0a884439fdcba06cf1b5a3e78d5e207
+size 2419596000

model-00011-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5368924cd2b65ae48a0e27c2e7af2c709a277a6bcd889ff369f6805282e364b
+size 2419596824

model-00012-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0a678458837a2849c330e940ad1876d25c22ec6ad195188b1073a326056b0f
+size 743249264

model-00013-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b542c62b7f740ea213139d345d3ae764d38b0dba562e6f515e0bf430a6e6cd
+size 2690128424

model-00014-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf169fc12c95701d9b0f924a83e58b3c366175fda5ead9e833bbeca1104074b4
+size 2419596728

model-00015-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7bc83bace663c712697ab281fab5ae89d56e57e9474b34b0a4fe6274be23be
+size 2690158096

model-00016-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4acbeac4e6797022c30eeb90bc11572e05672988104df8cf8d863b166c75ed0f
+size 2419595936

model-00017-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd617538d3769d0d9f4432998bcaea719bf7f2c77e8a02d5b94fc8bee809c79a
+size 2419596824

model-00018-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a508ef0cfa9c8fc9c3995ad2f92312920d0db7ddec2de6f7a36c7bc52496f631
+size 2690157720

model-00019-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982007cda68b2564716a933612bd4e84bc182dd792fd00de96169d6a19bdb84b
+size 2419596320

model-00020-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe89bb2e412c7d324f476bc05f32dc0d2472d7594b134fe5187e8d6ca4eea3a
+size 2419596832

model-00021-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34768aee903ec00ba779596a6303d5d8dcc3e6a70edb33d55f4a9733930085a9
+size 2690158440

model-00022-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9ee881a2eda67249bf04fe1c00f4a46289725070cb1da217d8ac995f5e2ddc
+size 2419597880

model-00023-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8750319707affbb5847a354485324f263e9273c69c6a0937c61719fbb04e27cc
+size 2690159256

model-00024-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa967ff8f5bba05b77dfacab3b56eb831abfa827ad8894493d219a87c78d9afe
+size 2419597088

model-00025-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c7a140e9fa2d84015d5b48762bcc1f9b6cbac0bb36a7eaba32a96b596237c8
+size 2419597992

model-00026-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c191f41090d86675ca4af706eeac2717ad7509d5646ad6c0184c824325be97
+size 2690158880

model-00027-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386f2e4cb50c1849b576eb7219bfc0961ce0a6b68581a3b2703874c552b5c693
+size 2419597456

model-00028-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac087c24ff7ddf2e61b978fc69e9efc06b661b44bb71a8aab3d592a3a40c8fb8
+size 2419597992

model-00029-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2abea2a6d3c06aeb161f723d0f10a70677e767c48d23ab5ee4db31d719788f
+size 2690158504

model-00030-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a2262f87535da1ef6396319861e1967d3b8eb2d7279f60fc6d9d1db4543896
+size 2419597840

model-00031-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7d93e5f1ab88a3a3b863f9f7651591eb81b5cc91e6a080e998665bd9026477
+size 2690159296

model-00032-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7fa97d7a73d959403633da4a6217e3d7d9bd43057c4dff4dbac8b18c05c0c47
+size 2419597048

model-00033-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ddef59ee08d7639759407744973038bb4b2eacf3bbfe2920629fcd30cb5a9c
+size 2419598000

model-00034-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169f972d86955c8cb23469eb206797038b41cbbcae0c0d8cd3888a2955fed038
+size 982731896

model-00035-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56fb8f6e4c403f93cd2749d56e75988cee7a3606b81bd52d0a2a6fbe0bc64ed
+size 2690129552

model-00036-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663537c4f8edb63e309c8e8664cceb80c17fffb370cb79ec1a10140b242af8f1
+size 2419597904

model-00037-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa66c35c84b8e5e32e04dfaba736a47cc55035bb18c656f402adecb91139a3ae
+size 2690159232

model-00038-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360d38f9e48b7200c9525cdb4742a07eb89bcb67f84d27414337905394d8b86a
+size 2419597112

model-00039-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aff94316d3b280687201fced1a8aefe8257ffa9f35d668cd8f17d59aab8816a
+size 2419597992

model-00040-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c445c2743a3bb3b4aa7e9795a3b7680ee01779006a06411beca88f1af895c2
+size 2690158848

model-00041-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479c7878ad1a39f51d912da9602865f42f38851fdf7dcedd0a5fa26097a35f41
+size 2419597488

model-00043-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2582049b2ff24855ac82b9bba52020781c863ff3f96da12c432803e28ea0e917
+size 2690158464

model-00044-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1927be919682684ae0439ba6b066964856365e29bb4fbdf23dc077b2184652c
+size 2419597880

model-00045-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be95db3b6c815d854909b37d8fab583cd3c4eb12d8860c379100a3f24ba34923
+size 2690159256

model-00047-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c4565f986bdf13c07b8714d2f20fa8b0f0efa8e87cd190c5c8a0930c8f252ff
+size 2419597992

model-00049-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ba1b2bcb575f5dfeb50f6cded516827816be5b71d60ccc48907ecd42f5e4ce
+size 2419597456